import org.apache.hadoop.io.Text; //导入方法依赖的package包/类
/**
* Read a line terminated by one of CR, LF, or CRLF.
*/
private int readDefaultLine(Text str, int maxLineLength, int maxBytesToConsume)
throws IOException {
/* We're reading data from in, but the head of the stream may be
* already buffered in buffer, so we have several cases:
* 1. No newline characters are in the buffer, so we need to copy
* everything and read another buffer from the stream.
* 2. An unambiguously terminated line is in buffer, so we just
* copy to str.
* 3. Ambiguously terminated line is in buffer, i.e. buffer ends
* in CR. In this case we copy everything up to CR to str, but
* we also need to see what follows CR: if it's LF, then we
* need consume LF as well, so next call to readLine will read
* from after that.
* We use a flag prevCharCR to signal if previous character was CR
* and, if it happens to be at the end of the buffer, delay
* consuming it until we have a chance to look at the char that
* follows.
*/
str.clear();
int txtLength = 0; //tracks str.getLength(), as an optimization
int newlineLength = 0; //length of terminating newline
boolean prevCharCR = false; //true of prev char was CR
long bytesConsumed = 0;
do {
int startPosn = bufferPosn; //starting from where we left off the last time
if (bufferPosn >= bufferLength) {
startPosn = bufferPosn = 0;
if (prevCharCR) {
++bytesConsumed; //account for CR from previous read
}
bufferLength = fillBuffer(in, buffer, prevCharCR);
if (bufferLength <= 0) {
break; // EOF
}
}
for (; bufferPosn < bufferLength; ++bufferPosn) { //search for newline
if (buffer[bufferPosn] == LF) {
newlineLength = (prevCharCR) ? 2 : 1;
++bufferPosn; // at next invocation proceed from following byte
break;
}
if (prevCharCR) { //CR + notLF, we are at notLF
newlineLength = 1;
break;
}
prevCharCR = (buffer[bufferPosn] == CR);
}
int readLength = bufferPosn - startPosn;
if (prevCharCR && newlineLength == 0) {
--readLength; //CR at the end of the buffer
}
bytesConsumed += readLength;
int appendLength = readLength - newlineLength;
if (appendLength > maxLineLength - txtLength) {
appendLength = maxLineLength - txtLength;
}
if (appendLength > 0) {
str.append(buffer, startPosn, appendLength);
txtLength += appendLength;
}
} while (newlineLength == 0 && bytesConsumed < maxBytesToConsume);
if (bytesConsumed > Integer.MAX_VALUE) {
throw new IOException("Too many bytes before newline: " + bytesConsumed);
}
return (int)bytesConsumed;
}